tasks-parallel-analysis — Claude Code rule: what it does
The tasks-parallel-analysis rule sets checks for marking tasks in tasks.md as parallel work. Use it when an agent drafts an implementation plan and needs to account for dependencies.
MIT ★ 3,774 updated 2026-10-22
.claude/rules/tasks-parallel-analysis.mdWhat tasks-parallel-analysis does
The rule allows a (P) marker only when a task has no pending data dependency, file or shared-resource conflict, or prerequisite approval. Earlier setup work must be complete, and _Boundary:_ annotations must show that the tasks cover separate components. Similar-looking tasks do not qualify on appearance alone.
Put (P) after the task number, outside the checkbox. Record dependencies and caveats in task details, and assess actionable subtasks rather than container tasks with no details of their own. When the requested mode is --sequential, omit all (P) markers. Shared resources can still cause merge or deployment conflicts, so the rule calls for checking them before marking work as parallel.
What it helps with
- mark tasks in
tasks.mdthat have no pending dependencies - separate component scopes with
_Boundary:_annotations - record a blocking dependency between tasks
- remove
(P)markers in sequential mode - check that each marked task can be tested independently
Example prompts for the agent
- Draft
tasks.mdand mark(P)only where dependencies and component boundaries allow parallel work. - Review
tasks.mdfor shared-file conflicts and add blocking dependencies to task details. - Create a sequential plan with
--sequentialand leave out every(P)marker.
How to install tasks-parallel-analysis
Manually: put the files in place
.claude/rules/tasks-parallel-analysis.mdThe paths frontmatter field limits the files
AGENTS.md
Codex reads AGENTS.md: paste the rule text there
Manually: put the files in place
.cursor/rules/tasks-parallel-analysis.mdcFrontmatter: description, globs, alwaysApply
Manually: put the files in place
.github/instructions/tasks-parallel-analysis.instructions.mdThe applyTo field sets which files it applies to
Manually: put the files in place
.devin/rules/tasks-parallel-analysis.mdManually: put the files in place
.clinerules/tasks-parallel-analysis.mdStep by step, with commands for each platform: AGENTS.md vs CLAUDE.md: what they are and which one to use
Questions about tasks-parallel-analysis
How do I install tasks-parallel-analysis in Claude Code?
Add the rule file at .claude/rules/tasks-parallel-analysis.md.
What does tasks-parallel-analysis do?
It defines checks for marking tasks.md items with (P). The checks cover dependencies, shared resources, setup work, and component boundaries.
When should a task not get a (P) marker?
Leave it unmarked if it depends on pending work, shares files or mutable resources, or needs prior approval. In --sequential mode, omit all (P) markers.
Source text
tasks-parallel-analysis.md · MIT
# Parallel Task Analysis Rules ## Purpose Provide a consistent way to identify implementation tasks that can be safely executed in parallel while generating `tasks.md`. ## Relationship to Task Ordering `(P)` means: this task has no dependency on its immediately preceding peers and can run concurrently with them. The Task Ordering Principle (see tasks-generation.md) ensures Foundation-phase tasks run first, making Core-phase tasks the primary `(P)` candidates. ## When to Consider Tasks Parallel Only mark a task as parallel-capable when **all** of the following are true: 1. **No data dependency** on pending tasks. 2. **No conflicting files or shared mutable resources** are touched. 3. **No prerequisite review/approval** from another task is required beforehand. 4. **Foundation work complete**: Environment/setup work needed by this task is already satisfied by earlier Foundation-phase tasks. 5. **Non-overlapping boundaries**: `_Boundary:_` annotations confirm tasks operate on separate components. ## Marking Convention - Append `(P)` immediately after the numeric identifier for each qualifying task. - Example: `- [ ] 2.1 (P) Build background worker for emails` - Apply `(P)` to both major tasks and sub-tasks when appropriate. - If sequential execution is requested (e.g. via `--sequential` flag), omit `(P)` markers entirely. - Keep `(P)` **outside** of checkbox brackets to avoid confusion with completion state. ## Grouping & Ordering Guidelines - Group parallel tasks under the same parent whenever the work belongs to the same theme. - List obvious prerequisites or caveats in the detail bullets (e.g., "Requires schema migration from 1.2"). - When two tasks look similar but are not parallel-safe, call out the blocking dependency explicitly. - Skip marking container-only major tasks (those without their own actionable detail bullets) with `(P)`—evaluate parallel execution at the sub-task level instead. ## Quality Checklist Before marking a task with `(P)`, ensure you have: - Verified that running this task concurrently will not create merge or deployment conflicts. - Confirmed `_Boundary:_` annotations show non-overlapping component scopes. - Captured any shared state expectations in the detail bullets. - Confirmed that the implementation can be tested independently. - Added `_Depends: X.X_` if this `(P)` task still requires specific prior work from a different major-task group. If any check fails, **do not** mark the task with `(P)` and explain the dependency in the task details.
© gotalab · MIT · gotalab/cc-sdd